© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78747
    Prev
    Next
    INDEX
    Explanations

    statements or claims regarding the truthfulness of information and rumors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wheeler
    -0.06
    fet
    -0.06
    tera
    -0.06
    Unified
    -0.06
    enz
    -0.05
    orman
    -0.05
    δια
    -0.05
    ingu
    -0.05
    ollower
    -0.05
     plateau
    -0.05
    POSITIVE LOGITS
     correct
    0.15
     truth
    0.14
     accurate
    0.14
     true
    0.14
    true
    0.14
     accuracy
    0.14
    truth
    0.13
     Accuracy
    0.12
    accur
    0.12
     truths
    0.11
    Activations Density 0.150%

    No Known Activations